gongliyu

Yolov5_DeepSort_Pytorch

Real-time multi-object tracker using YOLO v5 and deep sort

arlib

Common interfaces for archive manipulation

compfile

Common interfaces for manipulating compressed files (lzma, gzip etc)

csvf

C++ library and programs to handle large csv files: combine, split and read/write

decoutils

Utilities for writing decorators

.emacs.d

Liyu's Emacs config

csvfR

A pure R package to handle large csv file: split, merge, read/write row by row

deep-person-reid

Torchreid: Deep learning person re-identification in PyTorch.

GLPDepth

GLPDepth PyTorch Implementation: Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth

Grad-CAM

Gradient Class Activation Map implemented with PyTorch

HD-GCN

insightface

State-of-the-art 2D and 3D Face Analysis Project

PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle （practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices）

helm

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).

infogcn

Official implementation for "InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition"

LLMTest_NeedleInAHaystack

Doing simple retrieval from LLM models at various context lengths to measure accuracy

PaddleVideo

Comprehensive, latest, and deployable video deep learning algorithm, including video recognition, action localization, and temporal action detection tasks. It's a high-performance, light-weight codebase provides practical models for video understanding research and application

r-csvf

R package for fast processing of large csv files

st-gcn

Spatial Temporal Graph Convolutional Networks (ST-GCN) for Skeleton-Based Action Recognition in PyTorch